© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 15448
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лтемелер
    -0.63
    ing
    -0.51
    BPA
    -0.50
    AFTA
    -0.49
     XCTest
    -0.49
    Activité
    -0.47
    aneity
    -0.46
    parr
    -0.46
    ING
    -0.45
    arding
    -0.45
    POSITIVE LOGITS
     defaultstate
    0.64
     يتيمه
    0.64
    BagLayout
    0.60
    ⓧ
    0.58
     estekak
    0.56
     ModelExpression
    0.56
    splitContainer
    0.55
     CreateTagHelper
    0.55
    KommentareTeilen
    0.53
     contextLoads
    0.53
    Activations Density 0.045%

    No Known Activations